We Will Track You: A Multi-Criterion Evaluation of Modern Object Detectors for Lizard Behavioral Analysis

• Luis Gustavo de Oliveira Miranda UFOP
• Pedro Henrique Rabelo Leão de Oliveira UFOP
• Pedro Henrique Lopes Silva UFOP
• Vander Luis de Souza Freitas UFOP
• Eduardo José da Silva Luz UFOP
• Gladston Juliano Prates Moreira UFOP
• Conrado Aleksander Barbosa Galdino PUC Minas
• Jadson Castro Gertrudes UFOP

DOI: https://doi.org/10.5753/eniac.2026.30994

Resumo

Behavioral analysis of Tropidurus lizards historically relies on manual inspection of video recordings, which is time-consuming and labor-intensive. In this scenario, machine learning algorithms can help improve inspection efficiency and reduce time spent during evaluations. The present work investigates five recent object detectors for extracting ethological signals. We evaluate YOLOv5 as a baseline, YOLOv12, and three RT-DETR variants. The evaluation protocol integrates classical detection metrics and two ethological measures. Experimental results indicate that YOLOv12 presented the best result, balancing classical and temporal evaluation criteria.

Referências

Akiba, T., Sano, S., Yanase, T., Ohta, T., and Koyama, M. (2019). Optuna: A next-generation hyperparameter optimization framework. In Proc. ACM SIGKDD.

Alcock, J. (2009). Animal behavior: An evolutionary approach. Sinauer associates.

Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., and Zagoruyko, S. (2020). End-to-end object detection with transformers. In Computer Vision – ECCV 2020, pages 213–229.

Carpenter, C. C. and Ferguson, G. W. (1977). Variation and evolution of stereotyped behavior in reptiles. Biology of the Reptilia, 7:335–554.

Chan, A. H. H., Putra, P., Schupp, H., Köchling, J., Straßheim, J., Renner, B., Schroeder, J., Pearse, W. D., Nakagawa, S., Burke, T., Griesser, M., Meltzer, A., Lubrano, S., and Kano, F. (2025). Yolo-behaviour: A simple, flexible framework to automatically quantify animal behaviours from videos. Methods in Ecology and Evolution, 16(4):760–774.

DeCourcy, K. R. and Jenssen, T. A. (1994). Structure and use of male headbob signals by the lizard Anolis carolinensis. Animal Behaviour, 47(2):251–262.

Dell, A. I., Bender, J. A., Branson, K., Couzin, I. D., de Polavieja, G. G., Noldus, L. P., Pérez-Escudero, A., Perona, P., Straw, A. D., Wikelski, M., and Brose, U. (2014). Automated image-based tracking and its application in ecology. Trends Ecol. Evol., 29(7):417–428.

Ferrante, G. S., Rodrigues, F. M., Andrade, F. R. H., Goularte, R., and Meneguette, R. I. (2021). Understanding the state of the art in animal detection and classification using computer vision technologies. In Proc. IEEE Int. Conf. Big Data, pages 3056–3065.

Gou, J., Yu, B., Maybank, S. J., and Tao, D. (2021). Knowledge distillation: A survey. International Journal of Computer Vision, 129(6):1789–1819.

Kaplan, G. (2014). Animal communication. Wiley Interdisciplinary Reviews: Cognitive Science, 5(6):661–677.

Labra, A., Carazo, P., Desfilis, E., and Font, E. (2007). Agonistic interactions in a Liolaemus lizard: structure of head bob displays. Herpetologica, 63(1):11–18.

Li, H., Wu, Z., Shrivastava, A., and Davis, L. S. (2022). Rethinking pseudo labels for semi-supervised object detection. Proc. AAAI Conf. Artif. Intell., 36(2):1314–1322.

Li, Z., Xu, P., Chang, X., Yang, L., Zhang, Y., Yao, L., and Chen, X. (2023). When object detection meets knowledge distillation: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(8):10555–10579.

Martins, E. P., Labra, A., Halloy, M., and Thompson, J. T. (2004). Large-scale patterns of signal evolution: an interspecific study of Liolaemus lizard headbob displays. Animal Behaviour, 68(3):453–463.

Mathis, A., Mamidanna, P., Cury, K. M., Abe, T., Murthy, M. W., Mathis, M. W., and Bethge, M. (2018). Deeplabcut: markerless pose estimation of user-defined body parts with deep learning. Nature Neuroscience, 21(9):1281–1289.

Padilla, R., Passos, W. L., Dias, T. L. B., Netto, S. L., and da Silva, E. A. B. (2021). A comparative analysis of object detection metrics with a companion open-source toolkit. Electronics, 10(3).

Pereira, T. D., Aldarondo, D. E., Willmore, L., Kislin, M., Wang, S. S.-H., Murthy, M., and Shaevitz, J. W. (2019). Fast animal pose estimation using deep neural networks. Nature Methods, 16(1):117–125.

Rajagukguk, R. A., yeon Lee, S., yeon Park, J., Daniel, K. F., rin Lee, C., Chen, Z., Liu, D., Norton, T., Park, J., and woon Hong, S. (2025). Deep learning for visual animal monitoring (detection, tracking, pose estimation, and behavior classification): A comprehensive review. Smart Agricultural Technology, 12:101539.

Raza, A., Hanif, F., and Mohammed, H. A. (2025). Analyzing the enhancement of cnn-yolo and transformer based architectures for real-time animal detection in complex ecological environments. Scientific Reports, 15(1):39142.

Vicente, N. and Halloy, M. (2015). Male headbob display structure in a neotropical lizard, Liolaemus pacha: relation to social context. Herpetological Journal, 25(1):49–53.

Zenóbio, J. G. F., Silva, P. H. L., Luz, E. J. d. S., Moreira, G. J. P., Galdino, C. A. B., and Gertrudes, J. C. (2023). Reptilerecon: Um arcabouço para extração e análise de sinais de lagartos. Anais do Simpósio Brasileiro de Banco de Dados (SBBD).

Zhao, Y., Lv, W., Xu, S., Wei, J., Wang, G., Dang, Q., Liu, Y., and Chen, J. (2024). Detrs beat yolos on real-time object detection. In Proc. IEEE/CVF CVPR, pages 16965–16974.

Zhu, H., Wei, H., Li, B., Yuan, X., and Kehtarnavaz, N. (2020). A review of video object detection: Datasets, metrics and methods. Applied Sciences, 10(21).

Zou, Z., Chen, K., Shi, Z., Guo, Y., and Ye, J. (2023). Object detection in 20 years: A survey. Proceedings of the IEEE, 111(3):257–276.